End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google-t5/t5-small
 tags:
 - generated_from_trainer
+metrics:
+- rouge
 model-index:
 - name: tst-summarization
   results: []
@@ -15,6 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 # tst-summarization
 
 This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6220
+- Rouge1: 65.6704
+- Rouge2: 51.3605
+- Rougel: 65.6565
+- Rougelsum: 65.3846
+- Gen Len: 21.1074
 
 ## Model description
 

all_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 21.107355864811133,
+    "eval_loss": 0.6219637989997864,
+    "eval_rouge1": 65.6704,
+    "eval_rouge2": 51.3605,
+    "eval_rougeL": 65.6565,
+    "eval_rougeLsum": 65.3846,
+    "eval_runtime": 17.9666,
+    "eval_samples": 503,
+    "eval_samples_per_second": 27.996,
+    "eval_steps_per_second": 3.507,
+    "total_flos": 454479091040256.0,
+    "train_loss": 1.124249507675013,
+    "train_runtime": 54.6803,
+    "train_samples": 5149,
+    "train_samples_per_second": 282.497,
+    "train_steps_per_second": 8.833
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 21.107355864811133,
+    "eval_loss": 0.6219637989997864,
+    "eval_rouge1": 65.6704,
+    "eval_rouge2": 51.3605,
+    "eval_rougeL": 65.6565,
+    "eval_rougeLsum": 65.3846,
+    "eval_runtime": 17.9666,
+    "eval_samples": 503,
+    "eval_samples_per_second": 27.996,
+    "eval_steps_per_second": 3.507
+}

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

runs/Jun30_18-04-26_5bcf15f9-cbd7-4847-8c67-530b27aedefb/events.out.tfevents.1719770751.5bcf15f9-cbd7-4847-8c67-530b27aedefb.999.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00f37c2ed93e3552b72960abc0e238b9509dcca7647ff3ec779d77ca8fe2807
+size 613

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 454479091040256.0,
+    "train_loss": 1.124249507675013,
+    "train_runtime": 54.6803,
+    "train_samples": 5149,
+    "train_samples_per_second": 282.497,
+    "train_steps_per_second": 8.833
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 483,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 483,
+      "total_flos": 454479091040256.0,
+      "train_loss": 1.124249507675013,
+      "train_runtime": 54.6803,
+      "train_samples_per_second": 282.497,
+      "train_steps_per_second": 8.833
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 483,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 454479091040256.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}